LoRA for generating in the style of doujinshi artist Muchin.
MOSS
Trained on MOSS-Image-Base, tested on MOSS-Image-SFT
Examples made on default comfy workflow.
er_sde + simple, 50 steps, cfg 3, lora strength 1. Resolution - 2 mpx on multiple of 16.
Stating the obvious - to render in this style you need it to be illustration, 2d, anime, etc.
Tl:dr do not use it with realistic description if your goal is to emulate this style
Anima
Make sure to use keyword @Muchin
Tested on natural language, CLIP styled prompts and mix of them.
All of examples are made between 0.8 and 1.
Tested on turbo lora - not recommended for good genitalia .
Good with Anima RL lora for more details on 30 steps.
Quality tags masterpiece, best quality, score_7 and such are important.
Illustrious
Make sure to use keyword Muchin_style
Model is prone to fill the scene with characters, so use 'solo', '2girls' and negatives 'multiple characters', 'multiple girls', etc
neg recommended: (comic, koma, speech bubble, text, thought_bubble, onomatopoeia, censored, signature, bar_censor)Works with strength between 0.7-1, 1 can be glitchy depending on complexity of the prompt.
All of examples are made in 1, you need to be specific about the scene.